Quentin Fuxa
d337248fda
feat: add healthcheck to Dockerfiles ( #228 )
2026-02-20 20:48:28 +01:00
Quentin Fuxa
b8d9d7d289
fix: handle numpy object_ dtype from ctranslate2 encoder ( #337 )
2026-02-20 20:48:28 +01:00
Quentin Fuxa
4c7706e2cf
fix: use vac_chunk_size for audio processing interval when VAC is enabled ( #334 )
2026-02-20 20:48:06 +01:00
Quentin Fuxa
7f3a3df620
simulstreaming mlx & torch dedup of common base
2025-02-15 23:52:00 +01:00
Quentin Fuxa
e7e82f7c19
bump to 0.2.18
2026-02-11 22:10:00 +01:00
Quentin Fuxa
8c799fa4d1
fix simulstreaming vram leak: cap cross-attn accumulation + token budget
...
fixes #283 , fixes #275
- accumulated_cross_attns was growing unboundedly during decoding loop,
using up to ~5GB for repetition loops. now capped to rolling window of 16
- max_tokens_per_chunk was using TOKENS_PER_SECOND (mel frame rate = 50)
instead of actual text token rate (~15/s), allowing 10-40x too many
decoding steps
- removed unused torch.cat on early return path
- removed dead self.committed/last_result_tokens lists (never read)
- same fixes applied to mlx variant
2026-02-11 22:10:00 +01:00
Quentin Fuxa
8923337380
fix --direct-english-translation not setting task=translate for localagreement backends
...
the flag was only used for tokenizer language selection but never
actually passed to whisper/faster-whisper transcribe calls. also init
OpenaiApiASR.task and read from transcribe_kargs.
fixes #306
2026-02-11 22:10:00 +01:00
Quentin Fuxa
aded1649ae
fix model_cache_dir + direct_english_translation task in simulstreaming
...
pass actual cache dir instead of None, and use proper task string
instead of boolean for AlignAttConfig
fixes #310
2026-02-11 22:10:00 +01:00
Quentin Fuxa
3b535e857a
fix NoneType concatenation in add_translation
...
fixes #296
2026-02-11 22:10:00 +01:00
Quentin Fuxa
d649250b9a
fix Segment classmethod call + isinstance type narrowing
...
fixes #331 , fixes #329
2026-02-11 22:10:00 +01:00
Quentin Fuxa
7735478286
add insert_audio_chunk to DiartDiarization
...
fixes #332
2026-02-11 22:10:00 +01:00
Quentin Fuxa
b9e72d2b9a
add probability field to ASRToken
...
fixes #330 , fixes #313
2026-02-11 22:10:00 +01:00
Quentin Fuxa
e5b01033af
add json normalizers for english language in build
2026-01-16 10:47:46 +01:00
Quentin Fuxa
6ae545bcb1
bump to 0.2.17.post1
2026-01-16 10:43:52 +01:00
Quentin Fuxa
04980d3f5e
Merge branch 'main' of https://github.com/QuentinFuxa/WhisperLiveKit
2026-01-16 10:38:29 +01:00
Quentin Fuxa
79a705c969
fixes #323
2026-01-16 10:38:07 +01:00
Quentin Fuxa
34e4abd455
Merge pull request #322 from eschmidbauer/fix/thread-safety-issues
...
Fix kv cache not being properly cleaned between sessions
2026-01-09 19:23:35 +01:00
Emmanuel Schmidbauer
d59ddbaeae
Fix critical thread safety issues
2026-01-09 11:23:19 -05:00
Quentin Fuxa
4dd66e7766
Merge pull request #317 from jantonj/fix-bug-diarization-lag
...
update diarization lag after stream analysed
2025-12-19 17:43:07 +01:00
Anton Jacobson
3db5d81a20
update diarization lag after stream analysed
2025-12-18 14:13:28 +01:00
Quentin Fuxa
b67ddea494
bump to 0.2.17
2025-12-08 23:52:00 +01:00
Quentin Fuxa
3192553e20
fixes #307
2025-12-09 10:27:49 +01:00
Quentin Fuxa
f379a243fe
Merge pull request #274 from blakkd/patch-1
...
minor path change
2025-12-09 10:10:32 +01:00
Quentin Fuxa
ec09898a9f
fixes #301
2025-12-06 10:19:50 +01:00
blakkd
befbae56c7
minor path change
...
prevents
```
FileNotFoundError: [Errno 2] No such file or directory: 'whisperlivekit/web/live_transcription.html'
```
2025-11-16 23:47:58 +01:00
Quentin Fuxa
bbd4fd6cff
Merge branch 'improve_EOS_handling'
2025-11-16 22:30:31 +01:00
Quentin Fuxa
28985962a0
Silence handling: finish transcription even if not validated at the BEGINNING of the silence
2025-11-16 22:29:08 +01:00
Quentin Fuxa
a38c103fcd
simulstreaming coreml encoder compatibility
2025-11-16 21:24:14 +01:00
Quentin Fuxa
4d2ffb24f8
coreml conversion
2025-11-16 19:11:43 +01:00
Quentin Fuxa
1bbbb7903c
lora loader in shared whisper core
2025-11-16 18:44:35 +01:00
Quentin Fuxa
bcffdbc6b3
bump to 0.2.14
2025-11-15 20:19:09 +01:00
Quentin Fuxa
80b77998f9
Refactor backend handling
2025-11-15 19:51:41 +01:00
Quentin Fuxa
d310f7e25f
hf compatibility
2025-11-15 18:34:19 +01:00
Quentin Fuxa
8d9be88fe6
translation buffer is now displayed in frontend
2025-11-10 15:22:26 +01:00
Quentin Fuxa
16461052ed
task to direct-english-translation
2025-11-10 13:20:26 +01:00
Quentin Fuxa
5491dbd824
last_validated_token handled in state
2025-11-10 13:18:52 +01:00
Quentin Fuxa
13401ffe24
whisper core at root of wlk
2025-11-10 12:17:18 +01:00
Quentin Fuxa
7108d2ddc5
fixes https://github.com/QuentinFuxa/WhisperLiveKit/issues/269
2025-11-09 20:08:18 +01:00
Quentin Fuxa
a732e0903e
Add a script to detect alignement heads, usefull for distilled whisper
2025-11-09 18:12:09 +01:00
Quentin Fuxa
0491681be4
Distilled model compatibility with HF config.json to ModelDimensions
2025-11-08 20:20:05 +01:00
Quentin Fuxa
ffe5284764
_processing_tasks_done checks task completion
2025-11-05 23:34:00 +01:00
Quentin Fuxa
41ca17acda
to 0.2.13
2025-10-30 23:30:49 +01:00
Quentin Fuxa
06b31f51eb
exception when translation and no nllw
2025-10-30 23:30:19 +01:00
Quentin Fuxa
ece02db6a3
Use optional new separate NLLW package for translation
2025-10-30 19:36:28 +01:00
Quentin Fuxa
939a7ebf8b
Translation Local Agreement + Cache optimization v0. Not connected yet
2025-10-28 00:16:52 +01:00
Quentin Fuxa
61edb70fff
audioProcessor state variables are now uniquely in State dataclass
2025-10-26 18:54:47 +01:00
Quentin Fuxa
4e455b8aab
translation now separates validated from output buffer tokens
2025-10-26 18:51:09 +01:00
Quentin Fuxa
9434390ad3
simplify task stopping condition
2025-10-26 17:26:43 +01:00
Quentin Fuxa
65250db92c
tensor to list at the stream end
2025-10-26 16:40:12 +01:00
Quentin Fuxa
416dce7975
fixes #261
...
Co-authored-by: yosagi <11404771+yosagi@users.noreply.github.com >"
2025-10-25 14:20:08 +02:00
